EP3767415B1 - Vorrichtung, verfahren und computerprogramm zur erkennung anormaler einrichtungen - Google Patents

Vorrichtung, verfahren und computerprogramm zur erkennung anormaler einrichtungen Download PDF

Info

Publication number
EP3767415B1
EP3767415B1 EP18915139.2A EP18915139A EP3767415B1 EP 3767415 B1 EP3767415 B1 EP 3767415B1 EP 18915139 A EP18915139 A EP 18915139A EP 3767415 B1 EP3767415 B1 EP 3767415B1
Authority
EP
European Patent Office
Prior art keywords
path
path pattern
quality
production
devices
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
EP18915139.2A
Other languages
English (en)
French (fr)
Other versions
EP3767415A4 (de
EP3767415A1 (de
Inventor
Masashi TATEDOKO
Tsuyoshi Higuchi
Kiyoto Kawauchi
Takeshi Yoneda
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Mitsubishi Electric Corp
Original Assignee
Mitsubishi Electric Corp
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Mitsubishi Electric Corp filed Critical Mitsubishi Electric Corp
Publication of EP3767415A1 publication Critical patent/EP3767415A1/de
Publication of EP3767415A4 publication Critical patent/EP3767415A4/de
Application granted granted Critical
Publication of EP3767415B1 publication Critical patent/EP3767415B1/de
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B19/00—Programme-control systems
    • G05B19/02—Programme-control systems electric
    • G05B19/418—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM]
    • G05B19/4184—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM] characterised by fault tolerance, reliability of production system
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B19/00—Programme-control systems
    • G05B19/02—Programme-control systems electric
    • G05B19/418—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM]
    • G05B19/4185—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM] characterised by the network communication
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B19/00—Programme-control systems
    • G05B19/02—Programme-control systems electric
    • G05B19/418—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM]
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B19/00—Programme-control systems
    • G05B19/02—Programme-control systems electric
    • G05B19/418—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM]
    • G05B19/41845—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM] characterised by system universality, reconfigurability, modularity
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B19/00—Programme-control systems
    • G05B19/02—Programme-control systems electric
    • G05B19/418—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM]
    • G05B19/41865—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM] characterised by job scheduling, process planning, material flow
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B23/00—Testing or monitoring of control systems or parts thereof
    • G05B23/02—Electric testing or monitoring
    • G05B23/0205—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults
    • G05B23/0218—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterised by the fault detection method dealing with either existing or incipient faults
    • G05B23/0221—Preprocessing measurements, e.g. data collection rate adjustment; Standardization of measurements; Time series or signal analysis, e.g. frequency analysis or wavelets; Trustworthiness of measurements; Indexes therefor; Measurements using easily measured parameters to estimate parameters difficult to measure; Virtual sensor creation; De-noising; Sensor fusion; Unconventional preprocessing inherently present in specific fault detection methods like PCA-based methods
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B23/00—Testing or monitoring of control systems or parts thereof
    • G05B23/02—Electric testing or monitoring
    • G05B23/0205—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults
    • G05B23/0218—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterised by the fault detection method dealing with either existing or incipient faults
    • G05B23/0224—Process history based detection method, e.g. whereby history implies the availability of large amounts of data
    • G05B23/0227—Qualitative history assessment, whereby the type of data acted upon, e.g. waveforms, images or patterns, is not relevant, e.g. rule based assessment; if-then decisions
    • G05B23/0232—Qualitative history assessment, whereby the type of data acted upon, e.g. waveforms, images or patterns, is not relevant, e.g. rule based assessment; if-then decisions based on qualitative trend analysis, e.g. system evolution
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B23/00—Testing or monitoring of control systems or parts thereof
    • G05B23/02—Electric testing or monitoring
    • G05B23/0205—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults
    • G05B23/0218—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterised by the fault detection method dealing with either existing or incipient faults
    • G05B23/0224—Process history based detection method, e.g. whereby history implies the availability of large amounts of data
    • G05B23/0227—Qualitative history assessment, whereby the type of data acted upon, e.g. waveforms, images or patterns, is not relevant, e.g. rule based assessment; if-then decisions
    • G05B23/0235—Qualitative history assessment, whereby the type of data acted upon, e.g. waveforms, images or patterns, is not relevant, e.g. rule based assessment; if-then decisions based on a comparison with predetermined threshold or range, e.g. "classical methods", carried out during normal operation; threshold adaptation or choice; when or how to compare with the threshold
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
    • G06Q10/06395—Quality analysis or management
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/04—Manufacturing
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B2219/00—Program-control systems
    • G05B2219/30—Nc systems
    • G05B2219/32—Operator till task planning
    • G05B2219/32222—Fault, defect detection of origin of fault, defect of product
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B23/00—Testing or monitoring of control systems or parts thereof
    • G05B23/02—Electric testing or monitoring
    • G05B23/0205—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
    • Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
    • Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
    • Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
    • Y02P90/30—Computing systems specially adapted for manufacturing

Definitions

  • the present invention relates to an apparatus, method and computer program for identifying a pattern of devices that produces a defective product in a production line where a product is produced via a plurality of devices.
  • Patent Literature 1 there is described a method for identifying a device suspected to be defective, in a production line of a factory or a plant, by visualizing a product quality for each device based on a quality of a product and a production path indicating devices through which the product has been produced.
  • US 2015/338847 A1 relates to a method and an apparatus for discovering equipment causing a product defect in a manufacturing process.
  • US 2005/251365 A1 relates to a system and a method for identifying a manufacturing tool causing a fault.
  • JP 2000 198051 A relates to a device and a method for extracting abnormality from facility flow.
  • the phenomenon described above may occur, e.g. when a hole made in Device 1 falls within a range of an allowable error but deviates to the left a little, a hole made in Device 2 falls within a range of an allowable error but deviates to the right a little, a screw inserted in Device 3 is accurately inserted at the center, and a screw inserted in Device 4 falls within a range of an allowable error but deviates to the left a little.
  • This phenomenon can be said that a defective product is produced due to a negative interaction between Device 2 and Device 4.
  • Patent Literature 1 With the method described in Patent Literature 1, it is possible to identify a single device that produces a defective product. However, it is not possible to identify a path pattern of devices that produces a defective product. In the above-mentioned example, it is not possible to identify a path pattern that produces a defective product when there is a pattern in which a product passes through Device 4 after Device 2.
  • a defective product may be produced through a path pattern in which Device 2 precedes Device 4 due to the negative interaction between Device 2 and Device 4.
  • the number of devices having a negative interaction is not limited to two, and there may be a situation in which a defective product is produced when the product passes through three or more devices.
  • the present invention has been made to solve the above-mentioned problem, and has an object to provide an apparatus, method and computer program, which can identify a sequential order of two or more devices that produces a defective product in a production line where a product is produced via a plurality of devices.
  • the apparatus, method and computer program according to the present invention have a configuration which can identify a sequential order of two or more devices that produces a defective product based on known data on the production path and the production path quality. As a result, it is possible to identify the sequential order of two or more devices that produces a defective product in the production line where the product is produced via the plurality of devices.
  • FIG. 1 is a configuration diagram of a first embodiment of the present invention.
  • a factory 301 includes various kinds of devices 10 to 15 for processing a product. Further, the factory 301 includes an apparatus for monitoring quality 302 configured to monitor a production path and a quality of a product to be produced. The apparatus for monitoring quality 302 transmits, to an apparatus for identifying defective products 101, information containing the production path and the quality of a product to be produced in the factory 301.
  • the apparatus for monitoring quality 302 is constructed by a computer.
  • the apparatus for monitoring quality 302 comprises a quality monitor 303 and a quality transmitter 304.
  • Those components 303 and 304 of the apparatus for monitoring quality 302 may be constructed by hardware, or may be implemented as software of programs to be executed by a CPU (not shown) of the apparatus for monitoring quality 302.
  • the quality monitor 303 is configured to monitor the production path and the quality of a product to be produced in the factory 301, and to create information containing the production path and the quality of a product.
  • the quality transmitter 304 is configured to transmit, to the apparatus for identifying defective products 101, information containing the production path and the quality of a product, which has been created by the apparatus for monitoring quality 302.
  • the apparatus for identifying Defective products 101 may be connected to a plurality of apparatus for monitoring quality 302 of a plurality of factories 301. Further, the apparatus for identifying defective products 101 may be connected to the plurality of apparatus for monitoring quality 302 through a network configuration in which the plurality of apparatus for monitoring quality 302 form hierarchical structure.
  • the apparatus for identifying defective products 101 is constructed by a computer.
  • the apparatus for identifying defective products 101 comprises a product information receiver 111, a production path extractor 112, a production path quality generator 113, a path pattern generator 114, an association relationship generator 115, a path pattern quality estimator 116, an defective path pattern identifier 117 and a storage region 120.
  • Those components 111 to 117 of the apparatus for identifying defective products 101 may be constructed by hardware, or may be implemented as software of programs to be executed by a CPU (not shown) of the apparatus for identifying defective products 101.
  • the product information receiver 111 is configured to receive information containing the production path and the quality of a product, which has been transmitted from the apparatus for monitoring quality 302, and to store the received information into product information 121 of the storage region 120.
  • FIG. 2A shows an example of data structure of the product information 121.
  • the product information 121 contains a product ID 211, a production path 212 and a product quality 213.
  • the product ID 211 is a unique identifier for identifying a product.
  • the production path 212 is a character string representing devices via which the product is produced and an order of passing through those devices.
  • the production path 212 is a character string of " ⁇ Device 1, Device 2, Device 3 ⁇ .”
  • the product quality 213 is information representing the quality of the product.
  • the product quality 213 takes a real number equal to or larger than 0 and equal to or smaller than 1, and a larger value indicates a higher quality.
  • the production path and the quality of a product may not be received at the same time.
  • the production path and the quality may be received in any order as long as the production path and the quality can be associated with each other by a separate product ID.
  • the production path extractor 112 is configured to extract, for each product, a production path through which the product is produced based on the product information 121 of FIG. 2A , to merge overlapped production paths, and to store the merged production path into production path information 122 of the storage region 120.
  • the production path quality generator 113 is configured to generate, for each production path extracted and merged by the production path extractor 112, a production path quality indicating a quality of a group of products produced through the production path, and to store the generated production path quality into the production path information 122 of the storage region 120.
  • FIG. 2B shows an example of data structure of the production path information 122.
  • the production path information 122 contains a production path ID 221, a production path 222 and a production path quality 223.
  • the production path ID 221 is a unique identifier for identifying a production path through which a product is produced.
  • the production path 222 is a character string representing devices via which the product is produced and an order of passing through those devices.
  • the production path quality 223 is information indicating a quality of a group of products produced through the production path.
  • the production path quality 223 is defined by the following expression. ⁇ log 1 ⁇ 1 ⁇ Total product qualities belonging to the same production path ID Number of products belonging to the same production path ID
  • the production path quality 223 takes a value of 0 when the production path quality 223 is normal, whereas the production path quality 223 takes a value other than 0 when the production path quality 223 is defective.
  • the magnitude of the value indicates a degree of defectiveness of a group of products produced through the production path.
  • the path pattern generator 114 is configured to generate a possible "path pattern(s)" representing devices via which a product is produced and an order of passing through those devices, based on the production path 222 of the production path information 122 of FIG. 2B , and to store the path pattern(s) into path pattern information 123 of the storage region 120.
  • Each of the "path pattern(s)" is a possible pattern representing devices via which a product is produced and an order of passing through those devices.
  • the path pattern(s) can be generated when the devices included in the production path information of FIG. 2B and the "number of indispensable devices," which is the number of devices that must be included in the pattern(s), are specified.
  • this path pattern matches three production paths, i.e. Path 1 ⁇ Device 1, Device 2, Device 3, Device 5 ⁇ , Path 2 ⁇ Device 1, Device 4 ⁇ and Path 3 ⁇ Device 1, Device 3, Device 2 ⁇ , among the production paths of FIG. 2B .
  • Path Pattern (Device 2)
  • this path pattern matches two production paths, i.e. Path 1 ⁇ Device 1, Device 2, Device 3, Device 5 ⁇ and Path 3 ⁇ Device 1, Device 3, Device 2 ⁇ , among the production paths of FIG. 2B .
  • Path Pattern (Device 3) matches two production paths, i.e. Path 1 ⁇ Device 1, Device 2, Device 3, Device 5 ⁇ and Path 3 ⁇ Device 1, Device 3, Device 2 ⁇ .
  • Path Pattern (Device 4) matches one production path, i.e. Path 2 ⁇ Device 1, Device 4 ⁇ .
  • Path Pattern (Device 5) matches one production path, i.e. Path 1 ⁇ Device 1, Device 2, Device 3, Device 5 ⁇ .
  • Path Pattern (Device 1, *, Device 2)
  • this pattern matches two production paths, i.e. ⁇ Device 1, Device 2, Device 3, Device 5 ⁇ and ⁇ Device 1, Device 3, Device 2 ⁇ among the production paths of FIG. 2B .
  • Path Pattern (Device 1, *, Device 2) matches a production path(s) in which the sequential order of Device 1 and Device 2 is included.
  • Path Pattern (Device 1, *, Device 2, *, Device 3), ..., (Device 5, *, Device 4, *, Device 3).
  • this pattern matches one production path, i.e. ⁇ Device 1, Device 2, Device 3, Device 5 ⁇ among the production paths of FIG. 2B .
  • Path Pattern (Device 1, *, Device 2, *, Device 5) matches a production path(s) in which the sequential order of Device 1, Device 2 and Device 5 is included.
  • FIG. 2C shows an example of data structure of the path pattern information 123.
  • the path pattern information 123 contains a path pattern ID 231, a path pattern 232 and a path pattern quality 233.
  • the path pattern ID 231 is a unique identifier for identifying a path pattern.
  • the path pattern 232 is a character string which represents a possible pattern(s) representing devices via which a product is produced and an order of passing through those devices. There may be a path pattern that does not match any one of production paths of FIG. 2B , and such a path pattern is excluded so as to reduce the amount of calculation.
  • the path pattern quality 233 is information indicating the quality of a group of products produced through a production path(s) matching the path pattern.
  • the path pattern quality 233 takes a value equal to or smaller than a predetermined threshold value when the path pattern quality 233 is normal, whereas the path pattern quality 233 takes a value larger than the threshold value when the path pattern quality 233 is defective.
  • the magnitude of the value indicates a degree of defectiveness of a group of products produced through the production path(s) matching the path pattern.
  • the path pattern quality 233 is unknown at the time of generation of a path pattern(s) by the path pattern generator 114, and is initialized by an expression enabling distinction from invalidity, for example "N/A".
  • the association relationship generator 115 is configured to extract an association relationship between the production path 222 and the path pattern 232 based on the production path information 122 of FIG. 2B and the path pattern information 123 of FIG. 2C , and to store the extracted association relationship into association relationship information 124 of the storage region 120.
  • FIG. 2D shows an example of data structure of the association relationship information 124.
  • the association relationship information 124 contains a production path ID 241 and a path pattern ID 242.
  • the production path ID 241 is an arrangement of production path IDs stored in the production path ID 221 of the production path information 122 of FIG. 2B in a row direction.
  • the path pattern ID 242 is an arrangement of path pattern IDs stored in the path pattern ID 231 of the path pattern information 123 of FIG. 2C in a column direction.
  • association relationship information 124 of FIG. 2D considering a cell at which the production path ID 241 and the path pattern ID 242 intersect with each other, for example a cell 243 at which Production Path 1 and Path Pattern 1 intersect with each other.
  • a cell 243 at which Production Path 1 and Path Pattern 1 intersect with each other.
  • Production Path 1 matches Path Pattern 1, "1" is stored in the cell 243.
  • Production Path 1 does not match Path Pattern 1, "0" is stored in the cell 243.
  • the path pattern quality estimator 116 is configured to estimate the quality of each path pattern, i.e. the quality of a group of products produced through the production path(s) matching the path pattern based on the association relationship information 124 of FIG. 2D and the production path quality 223 of the production path information 122 of FIG. 2B , and to store the estimated quality of each path pattern into the path pattern quality 233 of the path pattern information 123 of FIG. 2C .
  • An example of the method of estimating the path pattern quality 233 is estimating the path pattern quality on the assumption that the production path quality is obtained as a linear observation of the path pattern quality based on the association relationship between the production path and the path pattern.
  • the production path quality 223 of the production path information 122 of FIG. 2B , the path pattern quality 233 of the path pattern information 123 of FIG. 2C and the association relationship information 124 of FIG. 2D are set as a constant vector y , a variable vector x and a matrix A , respectively, and these are substituted into a definition expression of linear observation.
  • the following equation is obtained. ⁇ y ⁇ Ax ⁇
  • variable vector x is estimated by solving an optimization problem of calculating x that minimizes the following cost function under a constraint condition x ⁇ 0 . ⁇ y ⁇ Ax ⁇
  • the defective path pattern identifier 117 is configured to identify a path pattern(s) for which the value of the path pattern quality is equal to or larger than a predetermined threshold value as a "defective path pattern(s)" based on the path pattern information 123 of FIG. 2C including the estimated path pattern quality.
  • the defective path pattern identifier 117 is configured to extract a device(s) commonly included in the defective path pattern(s) as a device(s) suspected to be defective, and to identify the extracted device(s) in an order of degree of defectiveness.
  • a method of setting the order of degree of defectiveness is considered to be, for example setting the order by prioritizing devices commonly included in the defective path pattern(s) having a larger value of the path pattern quality.
  • the defective path pattern identifier 117 outputs the identified device(s) to a monitor (not shown) as a device(s) suspected to be defective such as failure or cyberattack from the outside.
  • Step S101 for each product, the production path extractor 112 extracts a production path through which the product is produced based on the product information 121 of FIG. 2A , and merges overlapped production paths.
  • the production path extractor 112 stores the extracted and merged production path into the production path information 122 of FIG. 2B as the production path ID 221 and the production path 222.
  • Step S102 for each production path, the production path quality generator 113 generates a production path quality indicating the quality of a group of products produced through the production path.
  • the production path quality generator 113 stores the generated production path quality into the production path information 122 of FIG. 2B as the production path quality 223.
  • the path pattern generator 114 specifies "1" as the "number of indispensable devices” described above based on the production path 222 of the production path information 122 of FIG. 2B , and generates a possible path pattern(s). There may be a path pattern that does not match any one of production paths of FIG. 2B , and such path pattern is excluded so as to reduce the amount of calculation.
  • the path pattern generator 114 stores the generated path pattern(s) into the path pattern information 123 of FIG. 2C as the path pattern ID 231 and the path pattern 232.
  • the path pattern quality 233 is initialized by an expression enabling distinction from invalidity, for example "N/A".
  • Step S104 the association relationship generator 115 extracts an association relationship between the production path 222 and the path pattern 232 based on the production path information 122 of FIG. 2B and the path pattern information 123 of FIG. 2C , and stores the extracted association relationship into the association relationship information 124 of FIG. 2D .
  • Step S105 the path pattern quality estimator 116 estimates the quality of each path pattern based on the association relationship information 124 of FIG. 2D and the production path quality 223 of the production path information 122 of FIG. 2B .
  • the path pattern quality estimator 116 stores the estimated quality of each path pattern into the path pattern information 123 of FIG. 2C as the path pattern quality 233.
  • Step S106 the path pattern generator 114 determines whether a predetermined exit condition is satisfied. Specifically, the path pattern generator 114 extracts, from the path pattern information 123 of FIG. 2C , all the path patterns for which the value of the path pattern quality is equal to or larger than a predetermined threshold value.
  • Step S106 If the number of path patterns extracted in Step S106 is equal to or larger than a predetermined value, or the number of times of execution of Step S105, i.e. the number of times of estimation of the path pattern quality is equal to or larger than a predetermined number of times, the path pattern generator 114 determines that the exit condition has been satisfied, and the process goes to Step S107. Otherwise, the path pattern generator 114 determines that the exit condition has not been satisfied, and the process goes to Step S108.
  • the path pattern generator 114 may compare the tendency of the path pattern quality estimated at the previous iteration with the tendency of the path pattern quality estimated at the current iteration to determine whether the comparison result converges to a predetermined range.
  • the path pattern generator 114 may record the number of path patterns extracted in Step S106 while incrementing the "number of indispensable devices" by one. And when the "number of indispensable devices" with the least number of extracted path patterns is identified, the path pattern generator 114 may determine that the exit condition is satisfied.
  • identifying the number of indispensable devices with the least number of extracted path patterns means that identifying the number of indispensable devices with the minimum value of the graph.
  • Step S107 the path pattern generator 114 increments the "number of indispensable devices" by one, and generates a possible path pattern(s).
  • the path pattern generator 114 stores the generated path pattern(s) into the path pattern information 123 of FIG. 2C .
  • the path pattern quality 233 is initialized by an expression enabling distinction from invalidity, for example "N/A”. After that, the process returns to Step S104.
  • the defective path pattern identifier 117 identifies, based on the path pattern information 123 of FIG. 2C , a path pattern (s) for which the value of the path pattern quality is equal to or larger than a predetermined threshold value, as a "defective path pattern(s)" suspected to produce a defective product.
  • the defective path pattern identifier 117 identifies a device(s) commonly included in the defective path pattern(s) identified in Step S108.
  • the defective path pattern identifier 117 outputs the identified device(s) to the monitor (not shown) as a device(s) suspected to be defective such as failure or cyberattack from the outside.
  • Path 1 to Path 20 there are twenty production paths, i.e. Path 1 to Path 20, and Device 1 to Device 5 are arranged on the way of those production paths.
  • the path pattern information 123 shown in FIG. 5 is obtained from the production path information 122 of FIG. 4 .
  • a path pattern(s) that does not match any one of production paths of FIG. 4 is excluded.
  • association relationship information 124 shown in FIG. 6 is obtained from the production path information 122 of FIG. 4 and the path pattern information 123 of FIG. 5 .
  • the description of "PT" in FIG. 6 means “Pattern”.
  • the path pattern quality 233 shown in FIG. 7 is estimated from FIG. 4 to FIG. 6 .
  • a product produced through a production path(s) matching a Path Pattern (Device 2, *, Device 3), i.e. a path pattern in which Device 3 is arranged after Device 2 and zero or more devices are arranged between Device 3 and Device 2, has low quality.
  • a Path Pattern (Device 2, *, Device 3)
  • Device 3 i.e. a path pattern in which Device 3 is arranged after Device 2 and zero or more devices are arranged between Device 3 and Device 2
  • products produced through other production paths has high quality.
  • the defective path pattern identifier 117 of the apparatus for identifying defective products 101 identifies (Device 2, *, Device 3) as a "defective path pattern" suspected to produce a defective product.
  • the apparatus for identifying defective products estimates a path pattern quality indicating the quality of a group of products produced through a production path matching a path pattern based on the association relationship between the production path and the path pattern and the production path quality, and identifies a path pattern suspected to produce a defective product based on the estimated path pattern quality.
  • FIG. 8 is a configuration diagram of a second embodiment of the present invention.
  • the second embodiment it is possible to handle a defective situation in which the path pattern quality worsens over time.
  • An apparatus for monitoring quality 2302 comprises a quality monitor 2303 and a quality transmitter 2304.
  • the quality monitor 2303 is configured to monitor the production path and the quality of a product produced in the factory 301 as well as the time of measuring the quality, and to create information containing the production path and the quality of a product as well as the time of measuring the quality.
  • the quality transmitter 2304 transmits, to the apparatus for identifying defective products 2101, the information containing the production path and the quality of a product as well as the time of measuring the quality which has been created by the apparatus for monitoring quality 2303.
  • the apparatus for identifying defective products 2101 comprises a product information receiver 2111, a production path extractor 2112, a production path quality generator 2113, a path pattern generator 2114, an association relationship generator 2115, a path pattern quality estimator 2116 and a defective path pattern identifier 2117.
  • Those components are constructed by adding a concept of the time of measuring the product quality to the apparatus for identifying defective products 101 in the first embodiment.
  • the data structure in the second embodiment is described with reference to FIG. 9A to FIG. 9D .
  • the data structure in the second embodiment is constructed by adding the concept of the time of measuring the product quality to the data structure in the first embodiment.
  • FIG. 9A shows an example of data structure of a product information 1010 in the second embodiment.
  • the product information 1010 contains a product ID 1011, a production path 1012, a quality measurement time 1013 and a product quality 1014.
  • the product ID 1011, the production path 1012 and the product quality 1014 are the identical as those contained in the product information 121 in the first embodiment.
  • the quality measurement time 1013 is a time at which the product quality has been measured.
  • FIG. 9B shows an example of data structure of a production path information 1020 in the second embodiment.
  • the production path information 1020 contains a production path ID 1021, a production path 1022, a measurement start time 1023, a measurement end time 1024 and a production path quality 1025.
  • the production path ID 1021, the production path 1022 and the production path quality 1025 are the identical as those contained in the production path information 122 in the first embodiment.
  • the measurement start time 1023 and the measurement end time 1024 are specified by the defective path pattern identifier 2117 described in detail later, and specify a range of time period of measuring the product qualities to be aggregated into the production path quality 1025. For example, if the measurement start time is specified as t1 and the measurement end time is specified as t2 respectively, only the product qualities measured between the time t1 and the time t2 are aggregated into the production path quality.
  • FIG. 9C shows an example of data structure of a path pattern information 1030 in the second embodiment.
  • the path pattern information 1030 contains a path pattern ID 1031, a path pattern 1032, a measurement start time 1033, a measurement end time 1034 and a path pattern quality 1035.
  • the path pattern ID 1031, the path pattern 1032 and the path pattern quality 1035 are the identical as those contained in the path pattern information 123 in the first embodiment.
  • the measurement start time 1033 is a time of starting to measure a production path quality matching the path pattern.
  • the measurement end time 1034 is a time of finishing to measure the production path quality matching the path pattern.
  • FIG. 9D shows an example of data structure of an association relationship information 1040 in the second embodiment.
  • the association relationship information 1040 contains a production path ID 1041 and a path pattern ID 1042.
  • the production path ID 1041 and the path pattern ID 1042 are the identical as those contained in the association relationship information 124 in the first embodiment.
  • the flow chart of FIG. 10 is created by adding the concept of the time of measuring the product quality to the flow chart of FIG. 3 in the first embodiment.
  • the process of the flow chart of FIG. 10 is repeatedly called from Step S2201 of the flow chart of FIG. 11 described next.
  • Step S2101 for each product that the quality has been measured between the measurement start time and the measurement end time specified by the defective path pattern identifier 2117, the production path extractor 2112 extracts, a production path through which the product is produced based on the product information 1010 of FIG. 9A , and merges overlapped production paths.
  • the production path extractor 2112 stores the extracted and merged production path into the production path information 2020 of FIG. 9B as the production path ID 1021, the production path 1022, the measurement start time 1023 and the measurement end time 1024.
  • Step S2102 for each production path extracted and merged in Step S2101, the production path quality generator 2113 generates, a production path quality indicating the quality of a group of products produced through the production path.
  • the production path quality generator 2113 stores the generated production path quality into the production path information 1020 of FIG. 9B as the production path quality 1025.
  • the path pattern generator 2114 specifies "1" as the "number of indispensable devices” and generates a possible path pattern(s) based on the production path 1022 of the production path information 1020 of FIG. 9B .
  • the path pattern generator 2114 stores the generated path pattern(s) into the path pattern information 1030 of FIG. 9C as the path pattern ID 1031, the path pattern 1032, the measurement start time 1033 and the measurement end time 1034.
  • the path pattern quality 1035 is initialized by an expression enabling distinction from invalidity, for example "N/A".
  • Step S2104 the association relationship generator 2115 extracts an association relationship between the production path 1022 and the path pattern 1032 based on the production path information 1020 of FIG. 9B and the path pattern information 1030 of FIG. 9C , and stores the extracted association relationship into the association relationship information 1040 of FIG. 9D .
  • the path pattern quality estimator 2116 estimates the quality of each path pattern based on the association relationship information 1040 of FIG. 9D and the production path quality 1025 of the production path information 1020 of FIG. 9B .
  • the path pattern quality estimator 2116 stores the estimated quality of each path pattern into the path pattern information 1030 of FIG. 9C as the path pattern quality 1035.
  • Step S2106 the path pattern generator 2114 determines whether a predetermined exit condition is satisfied. Specifically, the path pattern generator 2114 extracts, from the path pattern information 1030 of FIG. 9C , all the path patterns for which the value of the path pattern quality is equal to or larger than a predetermined threshold value. If the number of extracted path patterns is equal to or larger than a predefined value, or the number of times of execution of Step S2105, i.e. the number of times of estimation of the path pattern quality is equal to or larger than a predetermined of number of times, the path pattern generator 2114 determines that the exit condition has been satisfied, and the process goes to Step S2108. Otherwise, the path pattern generator 2114 determines that the exit condition has not been satisfied, and the process goes to Step S2107.
  • Step S2107 the path pattern generator 2114 increments the "number of indispensable devices" by one, and generates a possible path pattern(s).
  • the path pattern generators 2114 stores the generated path pattern(s) into the path pattern information 1030 of FIG. 9C .
  • the path pattern quality 1035 is initialized by an expression enabling distinction from invalidity, for example "N/A”. After that, the process returns to Step S2104.
  • the defective path pattern identifier 2117 identifies, based on the path pattern information 1030 of FIG. 9C , a path pattern(s) for which the value of the path pattern quality is equal to or larger than a predetermined threshold value, as a "defective path pattern(s)" suspected to produce a defective product.
  • the defective path pattern identifier 2117 identifies a device(s) commonly included in the defective path pattern(s) identified in Step S2108.
  • the defective path pattern identifier 2117 outputs the identified device(s) to the monitor (not shown) as a device(s) suspected to be defective such as failure or cyberattack from the outside.
  • Step S2201 of the flow chart of FIG. 11 the process of the flow chart illustrated in FIG. 11 is repeatedly called from Step S2201 of the flow chart of FIG. 11 .
  • Step S2201 the defective path pattern identifier 2117 specifies a plurality of time ranges, and calls the process of the flow chart of FIG. 10 in the plurality of number of times. In each call, the defective path pattern identifier 2117 obtains all the path patterns included in FIG. 9C when the exit condition of Step S2106 of FIG. 10 is satisfied.
  • the following process is executed if first to third time ranges are specified, and the process of the flow chart of FIG. 10 is called in three times.
  • the defective path pattern identifier 2117 specifies a measurement start time t0 and a measurement end time t1 as the first time range, and calls the process of FIG. 10 . Then, the defective path pattern identifier 2117 obtains all the path patterns included in FIG. 9C when the exit condition of Step S2106 of FIG. 10 is satisfied.
  • the defective path pattern identifier 2117 specifies the measurement start time t1 and a measurement end time t2 as the second time range, and calls the process of FIG. 10 . Then, the defective path pattern identifier 2117 obtains all the path patterns included in FIG. 9C when the exit condition of Step S2106 of FIG. 10 is satisfied.
  • the defective path pattern identifier 2117 specifies the measurement start time t2 and a measurement end time t3 as the third time range, and calls the process of FIG. 10 . Then, the defective path pattern identifier 2117 obtains all the path patterns included in FIG. 9C when the exit condition of Step S2106 of FIG. 10 is satisfied.
  • Step S2202 the defective path pattern identifier 2117 goes to Step S2203 if there is a path pattern(s) for which the temporal transition of the path pattern quality for the past three times deviates from a predetermined range. Otherwise, the defective path pattern identifier 2117 finishes the process.
  • the defective path pattern identifier 2117 identifies the path pattern(s) for which the temporal transition of the path pattern quality for the past three times deviates from the predetermined range as a "defective path pattern(s)".
  • the defective path pattern identifier 2117 identifies a device(s) commonly included in the defective path pattern(s) identified in Step S2203.
  • the defective path pattern identifier 2117 outputs the identified device(s) to the monitor (not shown) as a device(s) suspected to be defective such as failure or cyberattack from the outside.
  • FIG. 12 shows an example of the temporal transition of the path pattern quality obtained by the apparatus for identifying defective products 2101 according to the second embodiment of the present invention.
  • the circles represent a case in which the value of the path pattern quality in each of time ranges T1 to T3 and the temporal transition of the value of the path pattern quality are both normal.
  • the symbol "Th" of FIG. 12 represents a predetermined threshold value, which is used in Step S2106 of FIG. 10 .
  • the triangles represent a case in which the value of the path pattern quality in the time range T2 is defective.
  • the squares represent a case in which the temporal transition of the value of the path pattern quality in each of the time ranges T1 to T3 is defective.
  • a region below the line R of FIG. 12 is a predetermined range, which is used in Step S2202 of FIG. 11 .
  • the apparatus for identifying defective products 2101 according to the second embodiment of the present invention further identifies a path pattern(s) for which the temporal transition of the value of the path pattern quality deviates from a predetermined range as a defective path pattern(s).

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Automation & Control Theory (AREA)
  • Business, Economics & Management (AREA)
  • Manufacturing & Machinery (AREA)
  • Quality & Reliability (AREA)
  • General Engineering & Computer Science (AREA)
  • Human Resources & Organizations (AREA)
  • Strategic Management (AREA)
  • Economics (AREA)
  • Marketing (AREA)
  • Development Economics (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Educational Administration (AREA)
  • Tourism & Hospitality (AREA)
  • General Business, Economics & Management (AREA)
  • Theoretical Computer Science (AREA)
  • General Health & Medical Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Primary Health Care (AREA)
  • Game Theory and Decision Science (AREA)
  • Operations Research (AREA)
  • General Factory Administration (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Claims (13)

  1. Vorrichtung (101; 2101) zum Identifizieren eines Wegmusters einer Vielzahl von Einrichtungen, welches ein fehlerhaftes Produkt in einer Fertigungslinie verursacht, in der ein Produkt über die Einrichtungen (10, 11, 12, 13, 14, 15) hergestellt wird, wobei die Vorrichtung aufweist:
    einen Fertigungsweg-Extraktor (112; 2112), der eingerichtet ist, einen Fertigungsweg, der die Einrichtungen, welche das Produkt bei seiner Herstellung durchläuft, sowie eine Reihenfolge, in welcher das Produkt die Einrichtungen durchläuft, angibt, auf der Grundlage von Produktinformationen, die von einer Vorrichtung zur Qualitätsüberwachung (302, 2302) übertragen werden, zu extrahieren;
    einen Fertigungsweg-Qualität-Generator (113; 2113), der eingerichtet ist, einen Fertigungsweg-Qualitätswert, der eine Qualität einer Gruppe von Produkten angibt, die über den Fertigungsweg hergestellt werden, zu generieren;
    einen Wegmuster-Generator (114; 2114), der eingerichtet ist, ein mögliches Wegmuster, das die Einrichtungen, die das Produkt bei seiner Herstellung durchläuft, und die Reihenfolge, in welcher das Produkt die Einrichtungen durchläuft, angibt, in Übereinstimmung mit einer Anzahl an unverzichtbaren Einrichtungen, die eine Anzahl von Einrichtungen angibt, die das Wegmuster aufweisen muss, zu generieren;
    einen Assoziationsbeziehung-Generator (115; 2115), der eingerichtet ist, eine Assoziationsbeziehung zwischen dem Fertigungsweg und dem Wegmuster zu generieren;
    einen Wegmuster-Qualität-Schätzer (116; 2116), der eingerichtet ist, einen Wegmuster-Qualitätswert, der eine Qualität der Gruppe von Produkten anzeigt, die durch den in dem Wegmuster einbezogenen Fertigungsweg hergestellt werden, auf der Grundlage der Assoziationsbeziehung und dem Produktionspfad-Qualitätswert zu schätzen; und
    einen Fehlerhafter-Weg-Identifikator (117; 2117), der eingerichtet ist, ein fehlerhaftes Wegmuster, für welches der Wert der Wegmusterqualität gleich oder größer als ein vorherbestimmter Schwellenwert ist, zu identifizieren.
  2. Vorrichtung nach Anspruch 1, wobei der Wegmuster-Generator (114; 2114) eingerichtet ist:
    einen Anfangswert für die Anzahl an unentbehrlichen Einrichtungen auf 1 setzen, um das Wegmuster zu generieren; und
    das Wegmuster wiederholt zu generieren, indem die Anzahl an unentbehrlichen Einrichtungen um eins inkrementiert wird, bis die Anzahl an fehlerhaften Wegmustern gleich oder größer als ein vorherbestimmter Wert ist.
  3. Vorrichtung nach Anspruch 1, wobei der Wegmuster-Generator (114; 2114) eingerichtet ist:
    einen Anfangswert für die Anzahl an unentbehrlichen Einrichtungen auf 1 setzen, um das Wegmuster zu generieren; und
    das Wegmuster wiederholt zu generieren, indem die Anzahl an unentbehrlichen Einrichtungen um eins inkrementiert wird, bis ein Vergleichsergebnis zwischen einer Tendenz eines ersten Wegmuster-Qualitätswerts, der bei einer vorherigen Iteration geschätzt wurde, und einer Tendenz eines zweiten Wegmuster-Qualitätswerts, der bei einer aktuellen Iteration geschätzt wurde, in einen vorherbestimmten Bereich konvergiert.
  4. Vorrichtung nach Anspruch 1, wobei der Wegmuster-Generator (114; 2114) eingerichtet ist:
    einen Anfangswert für die Anzahl an unentbehrlichen Einrichtungen auf 1 setzen, um das Wegmuster zu generieren; und
    das Wegmuster wiederholt zu generieren, indem die Anzahl an unentbehrlichen Einrichtungen um eins inkrementiert wird, bis die Anzahl an unentbehrlichen Einrichtungen mit der geringsten Anzahl an fehlerhaften Wegmustern identifiziert ist.
  5. Vorrichtung nach einem der Ansprüche 1 bis 4, wobei der Fehlerhafter-Wegpfad-Identifikator (2117) ferner eingerichtet ist, das Wegmuster, bei dem der zeitliche Übergang des Wertes der Wegmusterqualität von einem vorherbestimmten Bereich abweicht, als das fehlerhafte Wegmuster zu identifizieren.
  6. Vorrichtung nach einem der Ansprüche 1 bis 5, wobei der Fehlerhaftes-Wegmuster-Identifikator (117; 2117) ferner eingerichtet ist, eine Einrichtung, die üblicherweise in dem fehlerhaften Wegmuster einbezogen ist, als die Einrichtung zu identifizieren, von welcher vermutet wird, fehlerhaft zu sein, und die identifizierte Einrichtung in einer Reihenfolge des Grades der Fehlerhaftigkeit auszugeben.
  7. Verfahren zum Identifizieren eines Wegmusters einer Vielzahl von Einrichtungen, das ein fehlerhaftes Produkt in einer Fertigungslinie verursacht, in welcher ein Produkt über die Einrichtungen (10, 11, 12, 13, 14, 15) hergestellt wird, wobei das Verfahren die Schritte umfasst des:
    Extrahierens (S101; S2101) eines Fertigungswegs, welcher die Einrichtungen, die das Produkt bei seiner Herstellung durchläuft, und eine Reihenfolge, in welcher das Produkt die Einrichtungen durchläuft, angibt, auf der Grundlage von Produktinformationen, die von einer Vorrichtung zur Qualitätsüberwachung (302, 2302) übertragen werden;
    Generierens (S102; S2102) eines Fertigungsweg-Qualitätswertes, der eine Qualität einer Gruppe von Produkten angibt, die über den Fertigungsweg hergestellt werden;
    Generierens (5103, S107; 52103, S2107) eines möglichen Wegmusters, das die Einrichtungen, welche das Produkt bei seiner Herstellung durchläuft, und die Reihenfolge, in welcher das Produkt die Einrichtungen durchläuft, angibt, in Übereinstimmung mit einer Anzahl an unentbehrlichen Einrichtungen, die eine Anzahl von Einrichtungen angibt, die in dem Wegmuster einbezogen sein müssen;
    Generierens (S104; S2104) einer Assoziationsbeziehung zwischen dem Fertigungsweg und dem Wegmuster;
    Schätzens (S105; S2105) eines Wegmuster-Qualitätswertes, der eine Qualität der Gruppe von Produkten angibt, die durch den in dem Wegmuster enthaltenen Fertigungsweg hergestellt werden, auf der Grundlage der Assoziationsbeziehung und dem Produktionspfad-Qualitätswert; und
    Identifizierens (S108; S2108) eines defekten Wegmusters, für das der Wert der Wegmusterqualität gleich oder größer als ein vorherbestimmter Schwellenwert ist.
  8. Verfahren nach Anspruch 7, wobei der Schritt des Generierens (5103, S107; 52103, S2107) des Wegmusters umfasst:
    Setzen eines Anfangswerts für die Anzahl an unentbehrlichen Einrichtungen auf 1, um das Wegmuster zu generieren; und
    wiederholtes Generieren des Wegmusters, indem die Anzahl an unentbehrlichen Einrichtungen um eins inkrementiert wird, bis eine Anzahl an fehlerhaften Wegmustern gleich oder größer als ein vorherbestimmter Wert ist.
  9. Verfahren nach Anspruch 7, wobei der Schritt des Generierens (5103, S107; 52103, S2107) des Wegmusters umfasst:
    Setzen eines Anfangswerts für die Anzahl an unentbehrlichen Einrichtungen auf 1, um das Wegmuster zu generieren; und
    wiederholtes Generieren des Wegmusters, indem die Anzahl an unentbehrlichen Einrichtungen um eins inkrementiert wird, bis ein Vergleichsergebnis zwischen einer Tendenz eines ersten Wegmuster-Qualitätswerts, der bei einer vorherigen Iteration geschätzt wurde, und einer Tendenz eines zweiten Wegmuster-Qualitätswerts, der bei einer aktuellen Iteration geschätzt wurde, in einen vorherbestimmten Bereich konvergiert.
  10. Verfahren nach Anspruch 7, wobei der Schritt des Generierens (5103, S107; 52103, S2107) des Wegmusters umfasst:
    Setzen eines Anfangswerts für die Anzahl an unentbehrlichen Einrichtungen auf 1, um das Wegmuster zu generieren; und
    wiederholtes Generieren des Wegmusters, indem die Anzahl an unentbehrlichen Einrichtungen um eins inkrementiert wird, bis die Anzahl an unentbehrlichen Einrichtungen mit der geringsten Anzahl an fehlerhaften Wegmustern identifiziert ist.
  11. Verfahren nach einem der Ansprüche 7 bis 10, wobei der Schritt des Identifizierens des fehlerhaften Wegmusters ferner das Identifizieren (S2203) des Wegmusters, für welches der zeitliche Übergang des Wertes der Wegmusterqualität von einem vorherbestimmten Bereich abweicht, als das fehlerhafte Wegmuster umfasst.
  12. Verfahren nach einem der Ansprüche 7 bis 11, wobei der Schritt des Identifizierens des fehlerhaften Wegmusters ferner das Identifizieren (5109; 52109, 52204) einer Einrichtung, die üblicherweise in dem fehlerhaften Wegmuster enthalten ist, und das Ausgeben der identifizierten Einrichtung in einer Reihenfolge des Grades der Fehlerhaftigkeit umfasst.
  13. Computerprogramm, umfassend Anweisungen, die, wenn das Programm durch einen Computer ausgeführt wird, den Computer veranlassen, das Verfahren nach einem der Ansprüche 7 bis 12 auszuführen.
EP18915139.2A 2018-04-19 2018-04-19 Vorrichtung, verfahren und computerprogramm zur erkennung anormaler einrichtungen Active EP3767415B1 (de)

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/JP2018/016118 WO2019202700A1 (ja) 2018-04-19 2018-04-19 異常設備を特定する装置、方法、およびコンピュータプログラム

Publications (3)

Publication Number Publication Date
EP3767415A1 EP3767415A1 (de) 2021-01-20
EP3767415A4 EP3767415A4 (de) 2021-03-24
EP3767415B1 true EP3767415B1 (de) 2023-11-15

Family

ID=68240071

Family Applications (1)

Application Number Title Priority Date Filing Date
EP18915139.2A Active EP3767415B1 (de) 2018-04-19 2018-04-19 Vorrichtung, verfahren und computerprogramm zur erkennung anormaler einrichtungen

Country Status (7)

Country Link
US (1) US11215975B2 (de)
EP (1) EP3767415B1 (de)
JP (1) JP6811896B2 (de)
KR (1) KR102244169B1 (de)
CN (1) CN111954855B (de)
TW (1) TWI716755B (de)
WO (1) WO2019202700A1 (de)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2021131108A1 (ja) * 2019-12-27 2021-07-01 パナソニックＩｐマネジメント株式会社 品質推定装置および方法
WO2022244420A1 (ja) * 2021-05-19 2022-11-24 パナソニックＩｐマネジメント株式会社 不良予測システム、不良予測方法及びプログラム

Family Cites Families (26)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH08267344A (ja) * 1995-02-02 1996-10-15 Hitachi Ltd 生産方法及び薄膜ヘッドの製造方法
JP3950237B2 (ja) * 1998-08-10 2007-07-25 キヤノンシステムソリューションズ株式会社 製造計画作成方法及び記録媒体
JP2000198051A (ja) * 1998-12-29 2000-07-18 Matsushita Electric Ind Co Ltd 設備フロ―の異常抽出装置、設備フロ―の異常抽出方法、及び設備フロ―の異常抽出プログラムを記録した記憶媒体
JP2000269108A (ja) * 1999-03-15 2000-09-29 Sharp Corp 半導体製造装置の管理システム
JP2002094433A (ja) * 2000-09-12 2002-03-29 Hitachi Kokusai Electric Inc 異常検出システム
JP4413673B2 (ja) * 2004-03-29 2010-02-10 株式会社東芝 不良原因装置特定システム及び不良原因装置特定方法
JP4239932B2 (ja) * 2004-08-27 2009-03-18 株式会社日立製作所 生産管理システム
JP4772377B2 (ja) * 2005-05-13 2011-09-14 シャープ株式会社 異常設備推定装置、異常設備推定方法、異常設備推定プログラム、および、記録媒体
US7853431B2 (en) * 2006-09-29 2010-12-14 Fisher-Rosemount Systems, Inc. On-line monitoring and diagnostics of a process using multivariate statistical analysis
TWI330304B (en) * 2007-01-05 2010-09-11 Nupoint Technology Co Ltd Debug method for determining failure machines and application system thereof
JP2008226037A (ja) * 2007-03-14 2008-09-25 Omron Corp 生産管理システムおよび生産管理方法
JP4500876B1 (ja) 2009-01-20 2010-07-14 シャープ株式会社 生産管理システム
JP5251538B2 (ja) * 2009-01-20 2013-07-31 富士通株式会社 異常箇所特定プログラム、異常箇所特定装置、異常箇所特定方法
GB2496040B (en) * 2011-10-24 2019-04-03 Fisher Rosemount Systems Inc Predicted fault analysis
CN102637617B (zh) * 2012-05-09 2016-12-14 上海华虹宏力半导体制造有限公司 晶圆质量检测系统以及晶圆质量检测方法
CN102707679B (zh) * 2012-05-18 2015-12-09 Tcl王牌电器(惠州)有限公司 产线异常信息报告系统
JP6214889B2 (ja) * 2013-03-14 2017-10-18 株式会社東芝 プロセス監視診断装置
CN105917452B (zh) * 2013-11-27 2019-06-07 塞勒林特有限责任公司 用于半导体器件处理机吞吐量优化的方法和系统
CN103676868B (zh) * 2013-12-09 2016-06-29 华南理工大学 一种fpc制造关键工序自动监控与智能分析系统
JP6347622B2 (ja) 2014-02-14 2018-06-27 国立研究開発法人情報通信研究機構 ネットワークの故障検出方法
KR101466798B1 (ko) * 2014-05-20 2014-12-01 삼성전자주식회사 제조 공정에서의 제품 불량의 원인 설비를 탐지하는 방법 및 장치
JP6370132B2 (ja) * 2014-07-01 2018-08-08 西部電機株式会社 通信異常検出装置、通信異常検出方法及びプログラム
KR20160005995A (ko) * 2014-07-08 2016-01-18 현대오토에버 주식회사 품질불량 이력을 활용한 선제적 금형 예방관리시스템 및 그 운용 방법
CN106610584A (zh) * 2015-10-27 2017-05-03 沈阳工业大学 一种基于神经网络与专家系统的再制造工序质量控制方法
DE112016005697T5 (de) * 2016-01-15 2018-09-06 Mitsubishi Electric Corporation Vorrichtung, Verfahren und Programm zur Planerzeugung
JP6811018B2 (ja) * 2016-03-07 2021-01-13 三菱重工業株式会社 品質評価システム、品質評価方法及びプログラム

Also Published As

Publication number Publication date
CN111954855A (zh) 2020-11-17
JP6811896B2 (ja) 2021-01-13
TWI716755B (zh) 2021-01-21
KR102244169B1 (ko) 2021-04-23
EP3767415A4 (de) 2021-03-24
US20200401117A1 (en) 2020-12-24
CN111954855B (zh) 2024-05-14
WO2019202700A1 (ja) 2019-10-24
EP3767415A1 (de) 2021-01-20
TW201944187A (zh) 2019-11-16
KR20200125734A (ko) 2020-11-04
US11215975B2 (en) 2022-01-04
JPWO2019202700A1 (ja) 2020-07-27

Similar Documents

Publication Publication Date Title
CN106294120B (zh) 测试代码的方法、设备和计算机程序产品
US9239760B2 (en) Systems and methods for detecting, correcting, and validating bad data in data streams
US7107187B1 (en) Method for modeling system performance
EP3767415B1 (de) Vorrichtung, verfahren und computerprogramm zur erkennung anormaler einrichtungen
CN111611146A (zh) 一种微服务故障预测方法和装置
CN111881185A (zh) 一种数据监控方法、装置、设备及存储介质
EP3222000B1 (de) Ableitung von komponentenparametern für komponenten in einem netzwerk
CN107480051B (zh) 一种核电厂数字化反应堆保护系统软件测试系统及方法
US11133674B2 (en) System operation support device and method in power system, and wide-area monitoring protection control system
CN115576831A (zh) 一种测试案例推荐方法、装置、设备及存储介质
Koutsellis et al. Warranty forecasting of repairable systems for different production patterns
Mahmood et al. A method for extracting steady state components from Syncrophasor data using Kalman Filters
Krasich Modeling of SW reliability in early design with planning and measurement of its reliability growth
Park et al. A class of coverage growth functions and its practical application
CN113704763A (zh) 流水线式设备扫描探测方法
CN107885075B (zh) 一种对过程控制智能整定的检测方法及系统
Ginocchi et al. Global sensitivity analysis of state estimation for power distribution systems
CN116684327B (zh) 一种基于云计算的山林地区通信网络故障监测评估方法
CN113032227B (zh) 一种异常网元检测方法、装置、电子设备及存储介质
Luo et al. Software Reliability Growth Modelling using aWeighted Laplace Test Statistic
Vinodiya et al. Power system contingency ranking using fast decoupled load flow method
KR100381375B1 (ko) 이동 통신 정보 시스템에서 과부하 예측 방법
Okumoto An Overview of Practical Software Reliability Prediction
Moharil et al. Enhancement in Software Reliability Testing and Analysis
Palonen et al. Using car4ams, the Bayesian AMS data analysis code

Legal Events

Date Code Title Description
STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: THE INTERNATIONAL PUBLICATION HAS BEEN MADE

PUAI Public reference made under article 153(3) epc to a published international application that has entered the european phase

Free format text: ORIGINAL CODE: 0009012

STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: REQUEST FOR EXAMINATION WAS MADE

17P Request for examination filed

Effective date: 20201013

AK Designated contracting states

Kind code of ref document: A1

Designated state(s): AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR

AX Request for extension of the european patent

Extension state: BA ME

A4 Supplementary search report drawn up and despatched

Effective date: 20210224

RIC1 Information provided on ipc code assigned before grant

Ipc: G06Q 10/06 20120101ALI20210218BHEP

Ipc: G05B 19/418 20060101AFI20210218BHEP

Ipc: G05B 23/02 20060101ALI20210218BHEP

DAV Request for validation of the european patent (deleted)
DAX Request for extension of the european patent (deleted)
GRAP Despatch of communication of intention to grant a patent

Free format text: ORIGINAL CODE: EPIDOSNIGR1

STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: GRANT OF PATENT IS INTENDED

INTG Intention to grant announced

Effective date: 20230531

GRAS Grant fee paid

Free format text: ORIGINAL CODE: EPIDOSNIGR3

GRAA (expected) grant

Free format text: ORIGINAL CODE: 0009210

STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: THE PATENT HAS BEEN GRANTED

AK Designated contracting states

Kind code of ref document: B1

Designated state(s): AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR

REG Reference to a national code

Ref country code: CH

Ref legal event code: EP

Ref country code: GB

Ref legal event code: FG4D

P01 Opt-out of the competence of the unified patent court (upc) registered

Effective date: 20231018

REG Reference to a national code

Ref country code: DE

Ref legal event code: R096

Ref document number: 602018061313

Country of ref document: DE

REG Reference to a national code

Ref country code: IE

Ref legal event code: FG4D

REG Reference to a national code

Ref country code: LT

Ref legal event code: MG9D

REG Reference to a national code

Ref country code: NL

Ref legal event code: MP

Effective date: 20231115

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: GR

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20240216

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: IS

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20240315

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: LT

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20231115

REG Reference to a national code

Ref country code: AT

Ref legal event code: MK05

Ref document number: 1632344

Country of ref document: AT

Kind code of ref document: T

Effective date: 20231115

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: NL

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20231115

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: AT

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20231115

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: ES

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20231115

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: NL

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20231115

Ref country code: LT

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20231115

Ref country code: IS

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20240315

Ref country code: GR

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20240216

Ref country code: ES

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20231115

Ref country code: BG

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20240215

Ref country code: AT

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20231115

Ref country code: PT

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20240315

PGFP Annual fee paid to national office [announced via postgrant information from national office to epo]

Ref country code: GB

Payment date: 20240229

Year of fee payment: 7